Systems and methods for segmented risk scoring of identity fraud

• US 8,484,132 B1
• Filed: 06/08/2012
• Issued: 07/09/2013
• Est. Priority Date: 06/08/2012
• Status: Active Grant

• Current Assignee: LexisNexis Risk Solutions, Inc. (RELX PLC)
• Original Assignee: LexisNexis Risk Solutions, Inc. (RELX PLC)
• Inventors: Feinstein, Jeffrey Allen, Christiansen, James Alan, Yuan, Fang, Woodberry, Michael James, Sorenson, Brent Wayne
• Primary Examiner(s): Chang, Edward
• Application Number:
  US13/491,786
• Time in Patent Office: 396 Days
• Field of Search: 705/44, 705/35
• US Class Current: 705/44
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Abstract

Certain embodiments of the invention may include systems, methods, and apparatus for determining fraud risk associated with a credit application. According to an exemplary embodiment of the invention, a method is provided for receiving applicant information associated with the application; searching one or more consumer identity repositories for prior usage of the applicant information; generating a plurality of identity characteristics corresponding to the prior usage of the applicant information; assigning the application to one of a plurality of segments based at least in part on the searching; scoring the application with a predictive scoring model to determine a risk score based at least in part on the identity characteristics; determining identity fraud risk types associated with the application; and outputting the risk score and one or more indicators of the determined identity fraud risk types.

Claims

1. A method comprising executing computer executable instructions by one or more processors for determining fraud risk associated with a credit application, the method further comprising:

receiving applicant information associated with the application;

searching, by one or more computer processors, one or more consumer identity data repositories for prior usage of the applicant information;

generating, by the one or more computer processors, a plurality of identity characteristics corresponding to the prior usage of the applicant information;

assigning the application to one of a plurality of segments based at least in part on the searching, wherein assigning the application to at least one of the plurality of segments is based at least in part on applicant identity information that has only been reported by credit bureau sources;

scoring, by the one or more computer processors, the application with a predictive scoring model that uniquely corresponds to one or more of the plurality of segments for which the application is assigned to determine a risk score based at least in part on the identity characteristics, wherein the risk score provides an indication of a fraudulent application;

determining, by the one or more computer processors, identity fraud risk types associated with the application based at least in part on the identity characteristics; and

outputting, by the one or more computer processors, the risk score and one or more indicators of the determined identity fraud risk types.

2. The method of claim 1, wherein determining the identity fraud risk types comprises evaluating the application for one or more of the following:

a synthetic identity, a stolen identity, a manipulated identity, a vulnerable victim, a friend or family fraud, or a high risk identity with a record of suspicious activity.

3. The method of claim 1, wherein scoring the application with the predictive scoring model comprises utilizing a predictive scoring model that uniquely corresponds to the one of a plurality of segments for which the application is assigned.

4. The method of claim 1, wherein the assigning the application to one of a plurality of segments is further based on at least one of:

a social security number (SSN) that has been reported as associated with a deceased person;

a SSN that was issued prior to the declared date-of-birth on the application;

applicant identity information that matches at least part of corresponding search results information, but an associated address presented that has not previously been reported as a residential address for the applicant;

applicant identity information not previously reported by any available identity source;

applicant identity information that matches information reported by derogatory or law enforcement sources;

applicant identity information having elevated recent account opening activity;

or

applicant identity information that does not correspond to any of the other segments.

5. The method of claim 1, wherein scoring the application differentiates normal, low risk, and high fraud risk applications.

6. The method of claim 1, wherein receiving applicant information associated with the application comprises receiving one or more of the following:

a name, a phone number, a social security number, a date of birth, or an address.

7. The method of claim 1, wherein generating the plurality of identity characteristics comprises evaluating applicant information for one or more of the following:

social security number validation, address validation, characteristics of the address, issuance characteristics of the social security number, correlation of the individual identity elements in the consumer identity data repositories, velocity of the appearance of the identity in account opening searches, divergence between identity elements in account opening searches, history of the identity in the consumer identity data repositories, sources reporting the identity, associates and relatives of the identity, variation of the identity elements reported, or verification of the application identity as an existing identity known from consumer identity data repositories.

8. A system comprising:

At least one processor;

at least one memory for storing data and computer-executable instructions, wherein the processor is configured to access the at least one memory and further configured to execute the computer-executable instructions to;

receive applicant identity information associated with a credit application;

search one or more consumer identity data repositories for prior usage of the applicant information;

generate a plurality of identity characteristics corresponding to the prior usage of the applicant information;

assign the application to one of a plurality of segments based at least in part on the search, wherein assigning the application to at least one of the plurality of segments is based at least in part on applicant identity information that has only been reported by credit bureau sources;

score the application with a predictive scoring model that uniquely corresponds to one or more of the plurality of segments for which the application is assigned to determine a risk score based at least in part on the identity characteristics, wherein the risk score provides an indication of a fraudulent application;

determine identity fraud risk types associated with the application based at least in part on the identity characteristics; and

output the risk score and one or more indicators of the determined identity fraud risk types.

9. The system of claim 8, wherein the identity fraud risk types comprise one or more of the following:

a synthetic identity, a stolen identity, a manipulated identity, a vulnerable victim, a friend or family fraud, or a high risk identity with a record of suspicious activity.

10. The system of claim 8, wherein the predictive scoring model uniquely corresponds to the one of a plurality of segments for which the application is assigned.

11. The system of claim 8, wherein the application is assigned to the one of a plurality of segments based on at least in part on one of:

a social security number (SSN) that has been reported as associated with a deceased person;

a SSN that was issued prior to the declared date-of-birth on the application;

applicant identity information that matches at least part of corresponding search results information, but an associated address presented that has not previously been reported as a residential address for the applicant;

applicant identity information not previously reported by any available identity source;

applicant identity information that matches information reported by derogatory or law enforcement sources;

applicant identity information having elevated recent account opening activity;

or

applicant identity information that does not correspond to any of the other segments.

12. The system of claim 8, wherein the application is scored to differentiate normal, low risk, and high fraud risk applications.

13. The system of claim 8, wherein the applicant information comprises one or more of the following:

a name, a phone number, a social security number, a date of birth, or an address.

14. The system of claim 8, wherein the plurality of identity characteristics are generated based on one or more of the following:

social security number validation, address validation, characteristics of the address, issuance characteristics of the social security number, correlation of the individual identity elements in the consumer identity data repositories, velocity of the appearance of the identity in account opening searches, divergence between identity elements in account opening searches, history of the identity in the consumer identity data repositories, sources reporting the identity, associates and relatives of the identity, variation of the identity elements reported, or verification of the application identity as an existing identity known from consumer identity data repositories.

15. One or more non-transitory computer readable media comprising computer-executable instructions that, when executed by one or more processors, configure the one or more processors to:

receive applicant information associated with a credit application;

search one or consumer identity data repositories for prior usage of the applicant information;

generate a plurality of identity characteristics corresponding to the prior usage of the applicant information;

assign the application to one of a plurality of segments based at least in part on the search, wherein assigning the application to at least one of the plurality of segments is based at least in part on applicant identity information that has only been reported by credit bureau sources;

score the application with a predictive scoring model that uniquely corresponds to one or more of the plurality of segments for which the application is assigned to determine a risk score based at least in part on the identity characteristics, wherein the risk score provides an indication of a fraudulent application;

determine identity fraud risk types associated with the application based at least in part on the identity characteristics; and

output the risk score and one or more indicators of the determined identity fraud risk types.

16. The computer readable media of claim 15, wherein the identity fraud risk types comprise one or more of the following:

a synthetic identity, a stolen identity, a manipulated identity, a vulnerable victim, a friend or family fraud, or a high risk identity with a record of suspicious activity.

17. The computer readable media of claim 15, wherein the predictive scoring model uniquely corresponds to the one of a plurality of segments for which the application is assigned.

18. The computer readable media of claim 15, wherein the application is assigned to the one of a plurality of segments based on at least in part on one of:

a social security number (SSN) that has been reported as associated with a deceased person;

a SSN that was issued prior to the declared date-of-birth on the application;

applicant identity information that matches at least part of corresponding search results information, but an associated address presented that has not previously been reported as a residential address for the applicant;

applicant identity information not previously reported by any available identity source;

applicant identity information that matches information reported by derogatory or law enforcement sources;

applicant identity information having elevated recent account opening activity;

or

applicant identity information that does not correspond to any of the other segments.

19. The computer readable media of claim 15, wherein the application is scored to differentiate normal, low risk, and high fraud risk applications.

20. The computer readable media of claim 15, wherein the plurality of identity characteristics are generated based on one or more of the following:

social security number validation, address validation, characteristics of the address, issuance characteristics of the social security number, correlation of the individual identity elements in the consumer identity data repositories, velocity of the appearance of the identity in account opening searches, divergence between identity elements in account opening searches, history of the identity in the consumer identity data repositories, sources reporting the identity, associates and relatives of the identity, variation of the identity elements reported, or verification of the application identity as an existing identity known from consumer identity data repositories.